论文标题
摊销推理中的概括差距
Generalization Gap in Amortized Inference
论文作者
论文摘要
基于可能性的概率模型将其推广到看不见的数据的能力对于许多机器学习应用（例如无损压缩）至关重要。在这项工作中，我们研究了流行的概率模型类别的概括 - 变异自动编码器（VAE）。我们讨论了影响VAE的两个概括差距，并表明过度拟合通常由摊销推理主导。基于这一观察结果，我们提出了一个新的培训目标，以改善摊销推断的概括。我们演示了我们的方法如何在图像建模和无损压缩的背景下提高性能。
The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular class of probabilistic model - the Variational Auto-Encoder (VAE). We discuss the two generalization gaps that affect VAEs and show that overfitting is usually dominated by amortized inference. Based on this observation, we propose a new training objective that improves the generalization of amortized inference. We demonstrate how our method can improve performance in the context of image modeling and lossless compression.
